Diagnosis of Cancer Disease with High Accuracy via Petri Net Modeling of Signaling Pathways

Cancer remains a leading cause of death worldwide, affecting millions of people each year. There are many different types of cancer, including breast cancer, colon cancer and endometrial cancer, each with its own unique characteristics and challenges. One of the most crucial aspects of cancer management is early detection. Detecting cancer at an early stage significantly increases the chances of successful treatment and survival. In recent years, much research has been conducted to accelerate the diagnosis and prediction of cancer, especially by examining the role of genes, their effectiveness, and especially the sequence of changes in their activities in relation to this disease. An important part of the results of these studies has been related to KEGG signaling pathways. Many studies have also been conducted to model these signaling pathways via Petri net tools, which have shown good capabilities in this field. This article reveals in part some of these capabilities observed in a recently developed tool that provides a means for diagnosing various types of cancer by modeling their signaling pathways via Petri nets. Compared with other existing methods, the proposed method provides higher accuracy and precision (95–99%) on most related GEO datasets. With this method, blood samples, which are less expensive and easier to obtain for earlier detection, perform as well as tissue samples.